Retinal Image Fusion and Registration Libor Kubecka*, Jiri Jan* * Department of Biomedical...

1
Retinal Image Fusion and Registration Retinal Image Fusion and Registration Libor Kubecka*, Jiri Jan* Libor Kubecka*, Jiri Jan* * * Department of Biomedical Engineering, FEEC, B Department of Biomedical Engineering, FEEC, B rno rno U U niversity of niversity of T T echnology echnology , Czech , Czech Republic Republic EMBEC 2005, Prague, CZECH REPUBLIC 20.-25.11. 2005 Introduction HRT (Heildelberg Retina Thomograph) is widely used for imaging and following examination of the shape of the optic nerve head (ONH) and therefore for diagnosis glaucoma. For this purpose, correct segmentation of ONH is necessary but when manually performed also highly subjective and time consuming task. Unfortunately, current automatic segmentation algorithms are not sufficiently robust especially because the information of the ONH contour is sometimes missing in HRT images. Therefore, we hope that fusion of HRT image and colour fundus photograph will provide additional useable information. Here, the algorithms of image registration and fusion are described and results of ONH segmentation in fused images are presented. 2. Image Fusion via discrete wavelet decomposition (DWT) fusion decision map orthogonalisation by computation of maximal direction of linear operator L(I) (e.g. gradient of the vector-valued image I) from the norm of the first differential of L(I): Final orthogonalised value of the linear operator (given wavelet), – highest eigenvalue of matrix G, – its relevant eigenvector: 1. Image Registration Type: 2-dimensional, bi-modal, multi- resolutional, performed by optimization of global similarity metrics. Spatial transformation model: affine, perspective. Criterion: mutual information. Optimizers: controlled random search (CRS), Powell. Interpolation: nearest neighbour, partial volume. Registration results Acknowledgements Authors sincerely acknowledge the contribution of Prof. G. Michelson, Augen-Klinik Erlangen (Germany) who provided Kowa fundus camera images, data from Heidelberg Retina Tomograph and valuable consultations. Also Radim Chrastek’s contribution in optic disc segmentation phase is highly acknowledged. This project has been completed with support by the grant FRVŠ 3118/2005 (Ministry of Education, Czech republic) and also by the support of the research centre DAR (Ministry of Education, Czech Republic), proj. no. 1M6798555601. 4. Results We have successfully designed a registration method making use of robust optimization (controlled random search) of modified mutual information similarity criterion. Quality of the registration step has been evaluated by human observer and reaches 98% of successfully registered images. Further we applied a method for fusion of registered images based on wavelet transform and computation of maximal length of gradient of vector image. Finally, successful results of segmentation of optic disc contour has been presented. x x x I L d G d dy dx G G G G dy dx dy dx I L I L I L I L I L I L dy dx d T yy yx xy xx T n y n x n y n y n x n x T 2 2 2 dy L dx L d y x I I x I L y x y x y x y x , , , 1 1 1 1 I L Fusion rules = orthogonalisation blue red green DWT HRT IDWT Total number of images 334 Group I (precisly registered) 316 Group II (sligthly mis- registered) 13 Group III (mis-registered) 5 Sufficiently registered ( I+II) 329 Rate of succes [%] 98.5 Average mark 0.13 Mosaic (HRT, CFP) Registration schema HRT with overlaid edges from CFP 3. Segmentation For the purpose of segmentation, we modified Chrastek’s method for the case of fused image. This method consists of morphological operations for image preprocessing, Hough transform for circle fitting and anchored active contour model for the final fine segmentation of the optic nerve head. The qualitative evaluation of this step should be performed in the future. Fusion schema

Transcript of Retinal Image Fusion and Registration Libor Kubecka*, Jiri Jan* * Department of Biomedical...

Page 1: Retinal Image Fusion and Registration Libor Kubecka*, Jiri Jan* * Department of Biomedical Engineering, FEEC, Brno University of Technology, Czech Republic.

Retinal Image Fusion and RegistrationRetinal Image Fusion and Registration Libor Kubecka*, Jiri Jan*Libor Kubecka*, Jiri Jan*

* * Department of Biomedical Engineering, FEEC, BDepartment of Biomedical Engineering, FEEC, Brno rno UUniversity of niversity of TTechnologyechnology, Czech, Czech RepublicRepublic

EMBEC 2005, Prague, CZECH REPUBLIC 20.-25.11. 2005

IntroductionHRT (Heildelberg Retina Thomograph) is widely used for imaging and following examination of the shape of the optic nerve head (ONH) and therefore for diagnosis glaucoma. For this purpose, correct segmentation of ONH is necessary but when manually performed also highly subjective and time consuming task. Unfortunately, current automatic segmentation algorithms are not sufficiently robust especially because the information of the ONH contour is sometimes missing in HRT images. Therefore, we hope that fusion of HRT image and colour fundus photograph will provide additional useable information. Here, the algorithms of image registration and fusion are described and results of ONH segmentation in fused images are presented.

2. Image Fusion via discrete wavelet decomposition (DWT) fusion decision map – orthogonalisation by computation of maximal direction of linear operator L(I) (e.g. gradient of the vector-valued image I) from the norm of the first differential of L(I):

Final orthogonalised value of the linear operator (given wavelet), – highest eigenvalue of matrix G, – its relevant eigenvector:

1. Image Registration Type: 2-dimensional, bi-modal, multi-resolutional,

performed by optimization of global similarity metrics.

Spatial transformation model: affine, perspective. Criterion: mutual information. Optimizers: controlled random search (CRS), Powell. Interpolation: nearest neighbour, partial volume.

Registration results

AcknowledgementsAuthors sincerely acknowledge the contribution of Prof. G. Michelson, Augen-Klinik Erlangen (Germany) who provided Kowa fundus camera images, data from Heidelberg Retina Tomograph and valuable consultations. Also Radim Chrastek’s contribution in optic disc segmentation phase is highly acknowledged. This project has been completed with support by the grant FRVŠ 3118/2005 (Ministry of Education, Czech republic) and also by the support of the research centre DAR (Ministry of Education, Czech Republic), proj. no. 1M6798555601.

4. ResultsWe have successfully designed a registration method making use of robust optimization (controlled random search) of modified mutual information similarity criterion. Quality of the registration step has been evaluated by human observer and reaches 98% of successfully registered images. Further we applied a method for fusion of registered images based on wavelet transform and computation of maximal length of gradient of vector image. Finally, successful results of segmentation of optic disc contour has been presented.

xx

xIL

dGddy

dx

GG

GG

dy

dx

dy

dx

ILILIL

ILILIL

dy

dxd

T

yyyx

xyxxT

nynxny

nynxnx

T

2

22

dyLdxLd yx IIxIL

yx

yxyx

y

x

,

,,

11

11

IL

Fusion rules = orthogonalisation

blue

red

green

DWT

HRT

IDWT

Total number of images 334

Group I (precisly registered) 316

Group II (sligthly mis-registered) 13

Group III (mis-registered) 5

Sufficiently registered ( I+II) 329

Rate of succes [%] 98.5

Average mark 0.13

Mosaic (HRT, CFP)

Registration schema

HRT with overlaid edges from CFP

3. SegmentationFor the purpose of segmentation, we modified Chrastek’s method for the case of fused image. This method consists of morphological operations for image preprocessing, Hough transform for circle fitting and anchored active contour model for the final fine segmentation of the optic nerve head. The qualitative evaluation of this step should be performed in the future.

Fusion schema